comfyanonymous
c4c2db6ead
Add DualClipLoader to load clip models for SDXL.
...
Update LoadClip to load clip models for SDXL refiner.
2023-06-25 01:40:38 -04:00
comfyanonymous
818bae8e52
Fix CLIPLoader node.
2023-06-24 13:56:46 -04:00
comfyanonymous
391ee8d21f
Fix bug with controlnet.
2023-06-24 11:02:38 -04:00
Dr.Lt.Data
36d6488883
optimize: support preview mode for mask editor. ( #755 )
...
* support preview mode for mask editor.
* use original file reference instead of loaded frontend blob
bugfix:
* prevent file open dialog when save to load image
* bugfix: cannot clear previous mask painted image's alpha
* bugfix
* bugfix
---------
Co-authored-by: Lt.Dr.Data <lt.dr.data@gmail.com>
2023-06-24 03:45:41 -04:00
comfyanonymous
0db33017af
Add some more transformer hooks and move tomesd to comfy_extras.
...
Tomesd now uses q instead of x to decide which tokens to merge because
it seems to give better results.
2023-06-24 03:30:22 -04:00
comfyanonymous
51da619d73
Remove useless code.
2023-06-23 12:35:26 -04:00
comfyanonymous
a852d8b138
Move latent scale factor from VAE to model.
2023-06-23 02:33:31 -04:00
comfyanonymous
288f0c430d
Fix bug when yaml config has no clip params.
2023-06-23 01:12:59 -04:00
comfyanonymous
40f218c4fa
Fix error with ClipVision loader node.
2023-06-23 01:08:05 -04:00
comfyanonymous
6cb3519da6
Add SDXL support to readme and improve the Running section.
2023-06-22 19:33:48 -04:00
comfyanonymous
19c787b5d5
Merge branch 'master' of https://github.com/VladislavNekto/ComfyUI
2023-06-22 19:28:18 -04:00
comfyanonymous
4ed8aea1a1
Don't merge weights when shapes don't match and print a warning.
2023-06-22 19:08:31 -04:00
comfyanonymous
08f1f7686c
Support base SDXL and SDXL refiner models.
...
Large refactor of the model detection and loading code.
2023-06-22 13:03:50 -04:00
Vladislav
8b27e1252c
Update README.md
...
Information about running at RX7600
2023-06-22 22:23:47 +06:00
comfyanonymous
d72d5d49f5
Add original_shape parameter to transformer patch extra_options.
2023-06-21 13:22:01 -04:00
comfyanonymous
536af04958
Merge branch 'widget-input-overlapping' of https://github.com/ssitu/ComfyUI
2023-06-21 02:45:59 -04:00
comfyanonymous
c1ccf0b62b
Merge branch 'reroute-disconnect-fix' of https://github.com/ssitu/ComfyUI
2023-06-21 02:45:11 -04:00
comfyanonymous
cd8d0b73c5
Fix last commits causing an issue with the text encoder lora.
2023-06-20 19:44:39 -04:00
comfyanonymous
ae0bbb2264
Add some nodes for basic model merging.
2023-06-20 19:17:03 -04:00
comfyanonymous
af9e05f389
Keep a set of model_keys for faster add_patches.
2023-06-20 19:08:48 -04:00
comfyanonymous
2c71c47ff9
Add a type of model patch useful for model merging.
2023-06-20 17:34:11 -04:00
ssit
64961ef4e3
Fix reroute node connecting different types
2023-06-20 15:25:56 -04:00
ssit
196e870ca6
Fix overlapping when converting widgets to inputs
2023-06-20 12:03:46 -04:00
comfyanonymous
4ec26e7409
Merge branch 'improve-keyboard' of https://github.com/reaper47/ComfyUI
2023-06-20 00:54:04 -04:00
reaper47
e820a40a95
Clean keybinds extension
2023-06-19 21:32:21 +02:00
comfyanonymous
5384849e5e
Fix k_diffusion math being off by a tiny bit during txt2img.
2023-06-19 15:28:54 -04:00
comfyanonymous
873b08bd0f
Add a way to set patches that modify the attn2 output.
...
Change the transformer patches function format to be more future proof.
2023-06-18 22:58:22 -04:00
comfyanonymous
26bce56c3b
pop clip vision keys after loading them.
2023-06-18 21:21:17 -04:00
comfyanonymous
c1e1b00941
Not needed anymore.
2023-06-18 13:06:59 -04:00
comfyanonymous
78eabd0fd4
This is not needed anymore and causes issues with alphas_cumprod.
2023-06-18 03:18:25 -04:00
comfyanonymous
351d778487
Fix DDIM v-prediction.
2023-06-17 20:48:21 -04:00
comfyanonymous
257b565c12
Merge branch 'html5-dialog' of https://github.com/reaper47/ComfyUI
2023-06-17 18:39:55 -04:00
comfyanonymous
a98a8b31fd
Add bicubic upscale method.
2023-06-17 01:54:33 -04:00
comfyanonymous
a93a785f9e
Fix an issue when alphas_comprod are half floats.
2023-06-16 17:16:51 -04:00
comfyanonymous
d35c0ce6ec
All the unet weights should now be initialized with the right dtype.
2023-06-15 18:42:30 -04:00
comfyanonymous
e4077f2230
Update readme with command to install pytorch with ROCm5.5.
...
Remove mentions of python 3.10 since 3.11 works fine now.
2023-06-15 18:11:28 -04:00
comfyanonymous
282638b813
Add a --gpu-only argument to keep and run everything on the GPU.
...
Make the CLIP model work on the GPU.
2023-06-15 15:38:52 -04:00
comfyanonymous
8e6cbe6270
Initialize more unet weights as the right dtype.
2023-06-15 15:00:10 -04:00
comfyanonymous
206af9a315
Initialize transformer unet block weights in right dtype at the start.
2023-06-15 14:29:26 -04:00
reaper47
a8ad672927
Add missed .comfy-table in CSS
2023-06-15 18:39:18 +02:00
reaper47
0b3c1d68c8
Beautify settings dialog
2023-06-15 18:36:52 +02:00
comfyanonymous
a866f9288d
Fix server crashing because of terminated websocket connection.
2023-06-15 11:01:56 -04:00
comfyanonymous
16c535a309
Properly disable weight initialization in clip models.
2023-06-14 20:13:08 -04:00
comfyanonymous
6bbd86a061
Disable default weight values in unet conv2d for faster loading.
2023-06-14 19:46:08 -04:00
comfyanonymous
46a1fd77f4
This isn't needed for inference.
2023-06-14 13:05:08 -04:00
comfyanonymous
54c3f45d58
Don't initialize CLIPVision weights to default values.
2023-06-14 12:57:02 -04:00
comfyanonymous
0a80429175
Set model to fp16 before loading the state dict to lower ram bump.
2023-06-14 12:48:02 -04:00
comfyanonymous
3e75be0a92
Don't initialize clip weights to default values.
2023-06-14 12:47:36 -04:00
comfyanonymous
14508d7a5b
Speed up model loading a bit.
...
Default pytorch Linear initializes the weights which is useless and slow.
2023-06-14 12:09:41 -04:00
comfyanonymous
fb722705f9
Merge branch 'issue-752' of https://github.com/reaper47/ComfyUI
2023-06-14 00:17:25 -04:00
